论文部分内容阅读
将线性预测倒谱系数LPCC作为语音特征相似度的评价参数,采用欧氏距离来衡量语音的相似度,据此分析测试者语音与标准语音(或参考语音)间的偏差,以此给出测试者语音质量优劣的评价结果。该评价方法有助于语言学习者提高发音质量和朗读能力,并为语言口语教学评价提供一种新思路和新方法。
The linear predictive cepstrum coefficient LPCC is taken as the evaluation parameter for the similarity of speech features, the Euclidean distance is used to measure the similarity of the speech, and the deviation between the tester’s speech and the standard speech (or reference speech) is analyzed to give the test Voice quality advantages and disadvantages of the evaluation results. The evaluation method helps language learners improve pronunciation quality and reading ability, and provides a new idea and new method for the evaluation of spoken language teaching.